© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 244123
    Prev
    Next
    INDEX
    Explanations

    environment, image, must, location, manages, truffles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     governance
    0.54
     Governance
    0.47
    l
    0.47
    1
    0.46
     table
    0.46
     folder
    0.45
    MS
    0.45
    ation
    0.44
    9
    0.44
     $$
    0.43
    POSITIVE LOGITS
    üman
    0.51
     terão
    0.51
    positroid
    0.49
    ফাজ
    0.48
    irii
    0.48
     জায়
    0.48
     ঘিরে
    0.48
     সুরক্ষিত
    0.47
     falsa
    0.47
    ählten
    0.47
    Activations Density 0.000%

    No Known Activations